On Wed, 2002-09-18 at 19:07, Roman Zippel wrote:
> On Wed, 18 Sep 2002, Rusty Russell wrote:
>
> > +/* Stopping interrupts faster than atomics on many archs (and more
> > + easily optimized if they're not) */
> > +static inline void bigref_inc(struct bigref *ref)
> > +{
> > + unsigned long flags;
> > + struct bigref_percpu *cpu;
> > +
> > + local_irq_save(flags);
> > + cpu = &ref->ref[smp_processor_id()];
> > + if (likely(!cpu->slow_mode))
> > + cpu->counter++;
>
> Did you benchmark this? On most UP machines an inc/dec should be cheaper
> than irq enable/disable.
Yah. I would think due to pipeline effects, disabling interrupts would
never be faster than an atomic inc/dec, assuming the architecture has
normal locking.
Robert Love
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Mon Sep 23 2002 - 22:00:24 EST